© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 41493
    Prev
    Next
    INDEX
    Explanations

    configurations back saved

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    oyer
    -0.07
    æĮij
    -0.07
    è¿Ļç§įè¡Į为
    -0.06
    åºĶæīĭ
    -0.06
    oy
    -0.06
    ènement
    -0.06
    好
    -0.06
    形形èī²
    -0.06
    áš
    -0.06
    _destination
    -0.06
    POSITIVE LOGITS
    åĽŀåİ»
    0.10
    åĽŀåİ»äºĨ
    0.10
     ìĽIJëŀĺ
    0.09
     back
    0.09
    /original
    0.09
    åİŁ
    0.09
     tillbaka
    0.09
    -original
    0.08
    å¤įåİŁ
    0.08
     khôi
    0.08
    Activations Density 0.005%

    No Known Activations